© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34895
    Prev
    Next
    INDEX
    Explanations

    coming back strong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èµ·æĿ¥äºĨ
    -0.11
    åĩĽ
    -0.10
    æ·±å±Ĥ次
    -0.09
    æĽ´æ·±
    -0.09
    opot
    -0.09
    èģĶæĥ³
    -0.08
    æŃ£å®Ĺ
    -0.08
    èĩ¾
    -0.08
    ä¸įå°ıçļĦ
    -0.08
    æijĨåľ¨
    -0.08
    POSITIVE LOGITS
    neau
    0.10
    gom
    0.10
    /respond
    0.09
    rag
    0.09
    bern
    0.09
    anche
    0.09
    rou
    0.09
    нак
    0.09
    èĬ±æł·
    0.08
    neck
    0.08
    Activations Density 0.007%

    No Known Activations